Map-relative localization in lane-level maps for ADAS and autonomous driving

Future advanced driver assistant systems put high demands on the environmental perception especially in urban environments. Today's on-board sensors and on-board algorithms still do not reach a satisfying level of development from the point of view of robustness and availability. Thus, map data is often used as an additional data input to support the on-board sensor system and algorithms. The usage of map data requires a highly correct pose within the map even in cases of positioning errors by global navigation satellite systems or geometrical errors in the map data. In this paper we propose and compare two approaches for map-relative localization exclusively using a lane-level map. These approaches deliberately avoid the usage of detailed a priori maps containing point-landmarks, grids or road-markings. Additionally, we propose a grid-based on-board fusion of road-marking information and stationary obstacles addressing the problem of missing or incomplete road-markings in urban scenarios.